Search

Color constancy (CC) is one of the important perceptual abilities of the human visual system, which states that despite changes in illumination, the perceived colors of surfaces generally tend to remain constant. Nevertheless, the mechanisms underlying CC have been debated for several decades. A specific type of cell, known as the double opponent cell in the primary visual cortex (V1), is strongly implicated in achieving CC. However, the exact functioning manner of this cell type remains uncertain. In this work, our quantitative analysis of concentric double-opponent cells in V1 revealed their ability to identify gray surfaces within color-biased scenes. These gray surfaces can then be used to estimate the illumination easily. For the first time, this finding offers a clear functional explanation of concentric double-opponent receptive fields of this cell type in the visual system. Building on this insight, we introduced a novel computational theory--gray-anchoring (GA) theory--to explain how CC is achieved in the visual system. Specifically, GA-based CC involves detecting and anchoring gray surfaces within complex scenes. Our new theory serves as a bridge among the retinex theory, anchoring theory, and the neural mechanisms underlying visual CC in color vision., Comment: 12 pages, 3 figures

Out-of-Distribution (OOD) generalization in machine learning is a burgeoning area of study. Its primary goal is to enhance the adaptability and resilience of machine learning models when faced with new, unseen, and potentially adversarial data that significantly diverges from their original training datasets. In this paper, we investigate time series OOD generalization via pre-trained Large Language Models (LLMs). We first propose a novel \textbf{T}ri-level learning framework for \textbf{T}ime \textbf{S}eries \textbf{O}OD generalization, termed TTSO, which considers both sample-level and group-level uncertainties. This formula offers a fresh theoretic perspective for formulating and analyzing OOD generalization problem. In addition, we provide a theoretical analysis to justify this method is well motivated. We then develop a stratified localization algorithm tailored for this tri-level optimization problem, theoretically demonstrating the guaranteed convergence of the proposed algorithm. Our analysis also reveals that the iteration complexity to obtain an $\epsilon$-stationary point is bounded by O($\frac{1}{\epsilon^{2}}$). Extensive experiments on real-world datasets have been conducted to elucidate the effectiveness of the proposed method., Comment: Accepted at NeurIPS 2024

The one-dimensional side gate based on graphene edges shows a significant capability of reducing the channel length of field-effect transistors, further increasing the integration density of semiconductor devices. The nano-scale electric field distribution near the edge provides the physical limit of the effective channel length, however, its imaging under ambient conditions still lacks, which is a critical aspect for the practical deployment of semiconductor devices. Here, we used scanning nitrogen-vacancy microscopy to investigate the electric field distribution near edges of a single-layer-graphene. Real-space scanning maps of photo-charged floating graphene flakes were acquired with a spatial resolution of $\sim$ 10 nm, and the electric edge effect was quantitatively studied by analyzing the NV spin energy level shifts due to the electric Stark effect. Since the graphene flakes are isolated from external electric sources, we brought out a theory based on photo-thermionic effect to explain the charge transfer from graphene to oxygen-terminated diamond probe with a disordered distribution of charge traps. Real-time tracing of electric fields detected the photo-thermionic emission process and the recombination process of the emitted electrons. This study provides a new perspective for graphene-based one-dimensional gates and opto-electronics with nanoscale real-space imaging, and moreover, offers a novel method to tune the chemical environment of diamond surfaces based on optical charge transfer., Comment: 8 pages, 4 figures

Learning representations on large graphs is a long-standing challenge due to the inter-dependence nature. Transformers recently have shown promising performance on small graphs thanks to its global attention for capturing all-pair interactions beyond observed structures. Existing approaches tend to inherit the spirit of Transformers in language and vision tasks, and embrace complicated architectures by stacking deep attention-based propagation layers. In this paper, we attempt to evaluate the necessity of adopting multi-layer attentions in Transformers on graphs, which considerably restricts the efficiency. Specifically, we analyze a generic hybrid propagation layer, comprised of all-pair attention and graph-based propagation, and show that multi-layer propagation can be reduced to one-layer propagation, with the same capability for representation learning. It suggests a new technical path for building powerful and efficient Transformers on graphs, particularly through simplifying model architectures without sacrificing expressiveness. As exemplified by this work, we propose a Simplified Single-layer Graph Transformers (SGFormer), whose main component is a single-layer global attention that scales linearly w.r.t. graph sizes and requires none of any approximation for accommodating all-pair interactions. Empirically, SGFormer successfully scales to the web-scale graph ogbn-papers100M, yielding orders-of-magnitude inference acceleration over peer Transformers on medium-sized graphs, and demonstrates competitiveness with limited labeled data., Comment: Extended version of NeurIPS2023 contribution arXiv:2306.10759

In this article, we study the long-time dynamics of threshold solutions for the focusing energy-critical inhomogeneous Schr\"odinger equation and classify the corresponding threshold solutions in dimensions $d=3,4,5$. We first show the existence of special threshold solutions $W^\pm$ by constructing a sequence of approximate solutions in suitable Lorentz space, which exponentially approach the ground state $W$ in one of the time directions. We then prove that solutions with threshold energy either behave as in the subthreshold case or agree with $W, W^+$ or $W^-$ up to the symmetries of the equation. The proof relies on detailed spectral analysis of the linearized Schr\"odinger operator, the relevant modulation analysis, the global Virial analysis, and the concentration compactness argument in the Lorentz space.

The proliferation of misleading visualizations online, particularly during critical events like public health crises and elections, poses a significant risk. This study investigates the capability of GPT-4 models (4V, 4o, and 4o mini) to detect misleading visualizations. Utilizing a dataset of tweet-visualization pairs containing various visual misleaders, we test these models under four experimental conditions with different levels of guidance. We show that GPT-4 models can detect misleading visualizations with moderate accuracy without prior training (naive zero-shot) and that performance notably improves when provided with definitions of misleaders (guided zero-shot). However, a single prompt engineering technique does not yield the best results for all misleader types. Specifically, providing the models with misleader definitions and examples (guided few-shot) proves more effective for reasoning misleaders, while guided zero-shot performs better for design misleaders. This study underscores the feasibility of using large vision-language models to detect visual misinformation and the importance of prompt engineering for optimized detection accuracy., Comment: 5 pages, 2 figures; accepted by IEEE VIS 2024 (https://ieeevis.org/year/2024/program/paper_v-short-1177.html)

The National Science Foundation's Daniel K. Inouye Solar Telescope (DKIST) will provide high-resolution, multi-line spectropolarimetric observations that are poised to revolutionize our understanding of the Sun. Given the massive data volume, novel inference techniques are required to unlock its full potential. Here, we provide an overview of our "SPIn4D" project, which aims to develop deep convolutional neural networks (CNNs) for estimating the physical properties of the solar photosphere from DKIST spectropolarimetric observations. We describe the magnetohydrodynamic (MHD) modeling and the Stokes profile synthesis pipeline that produce the simulated output and input data, respectively. These data will be used to train a set of CNNs that can rapidly infer the four-dimensional MHD state vectors by exploiting the spatiotemporally coherent patterns in the Stokes profile time series. Specifically, our radiative MHD model simulates the small-scale dynamo actions that are prevalent in quiet-Sun and plage regions. Six cases with different mean magnetic fields have been conducted; each case covers six solar-hours, totaling 109 TB in data volume. The simulation domain covers at least $25\times25\times8$ Mm with $16\times16\times12$ km spatial resolution, extending from the upper convection zone up to the temperature minimum region. The outputs are stored at a 40 s cadence. We forward model the Stokes profile of two sets of Fe I lines at 630 and 1565 nm, which will be simultaneously observed by DKIST and can better constrain the parameter variations along the line of sight. The MHD model output and the synthetic Stokes profiles are publicly available, with 13.7 TB in the initial release., Comment: Submitted to AAS Journals after revision. Comments welcome

Multiple Instance Learning (MIL) has garnered widespread attention in the field of Whole Slide Image (WSI) classification as it replaces pixel-level manual annotation with diagnostic reports as labels, significantly reducing labor costs. Recent research has shown that bag-level MIL methods often yield better results because they can consider all patches of the WSI as a whole. However, a drawback of such methods is the incorporation of more redundant patches, leading to interference. To extract patches with high diagnostic value while excluding interfering patches to address this issue, we developed an attention-based feature distillation multi-instance learning (AFD-MIL) approach. This approach proposed the exclusion of redundant patches as a preprocessing operation in weakly supervised learning, directly mitigating interference from extensive noise. It also pioneers the use of attention mechanisms to distill features with high diagnostic value, as opposed to the traditional practice of indiscriminately and forcibly integrating all patches. Additionally, we introduced global loss optimization to finely control the feature distillation module. AFD-MIL is orthogonal to many existing MIL methods, leading to consistent performance improvements. This approach has surpassed the current state-of-the-art method, achieving 91.47% ACC (accuracy) and 94.29% AUC (area under the curve) on the Camelyon16 (Camelyon Challenge 2016, breast cancer), while 93.33% ACC and 98.17% AUC on the TCGA-NSCLC (The Cancer Genome Atlas Program: non-small cell lung cancer). Different feature distillation methods were used for the two datasets, tailored to the specific diseases, thereby improving performance and interpretability.

Task allocation is a key combinatorial optimization problem, crucial for modern applications such as multi-robot cooperation and resource scheduling. Decision makers must allocate entities to tasks reasonably across different scenarios. However, traditional methods assume static attributes and numbers of tasks and entities, often relying on dynamic programming and heuristic algorithms for solutions. In reality, task allocation resembles Markov decision processes, with dynamically changing task and entity attributes. Thus, algorithms must dynamically allocate tasks based on their states. To address this issue, we propose a two-stage task allocation algorithm based on similarity, utilizing reinforcement learning to learn allocation strategies. The proposed pre-assign strategy allows entities to preselect appropriate tasks, effectively avoiding local optima and thereby better finding the optimal allocation. We also introduce an attention mechanism and a hyperparameter network structure to adapt to the changing number and attributes of entities and tasks, enabling our network structure to generalize to new tasks. Experimental results across multiple environments demonstrate that our algorithm effectively addresses the challenges of dynamic task allocation in practical applications. Compared to heuristic algorithms like genetic algorithms, our reinforcement learning approach better solves dynamic allocation problems and achieves zero-shot generalization to new tasks with good performance. The code is available at https://github.com/yk7333/TaskAllocation.

Capturing molecular knowledge with representation learning approaches holds significant potential in vast scientific fields such as chemistry and life science. An effective and generalizable molecular representation is expected to capture the consensus and complementary molecular expertise from diverse views and perspectives. However, existing works fall short in learning multi-view molecular representations, due to challenges in explicitly incorporating view information and handling molecular knowledge from heterogeneous sources. To address these issues, we present MV-Mol, a molecular representation learning model that harvests multi-view molecular expertise from chemical structures, unstructured knowledge from biomedical texts, and structured knowledge from knowledge graphs. We utilize text prompts to model view information and design a fusion architecture to extract view-based molecular representations. We develop a two-stage pre-training procedure, exploiting heterogeneous data of varying quality and quantity. Through extensive experiments, we show that MV-Mol provides improved representations that substantially benefit molecular property prediction. Additionally, MV-Mol exhibits state-of-the-art performance in multi-modal comprehension of molecular structures and texts. Code and data are available at https://github.com/PharMolix/OpenBioMed., Comment: 12 pages, 4 figures

Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative offline RL algorithms struggle to generalize to unseen actions, despite their success in learning good in-distribution policy. In contrast, we propose to use the gradient fields of the dataset density generated from a pre-trained offline RL algorithm to adjust the original actions. We decouple the conservatism constraints from the policy, thus can benefit wide offline RL algorithms. As a consequence, we propose the Conservative Denoising Score-based Algorithm (CDSA) which utilizes the denoising score-based model to model the gradient of the dataset density, rather than the dataset density itself, and facilitates a more accurate and efficient method to adjust the action generated by the pre-trained policy in a deterministic and continuous MDP environment. In experiments, we show that our approach significantly improves the performance of baseline algorithms in D4RL datasets, and demonstrate the generalizability and plug-and-play capability of our model across different pre-trained offline RL policy in different tasks. We also validate that the agent exhibits greater risk aversion after employing our method while showcasing its ability to generalize effectively across diverse tasks.

Social media platforms allow users to create polls to gather public opinion on diverse topics. However, we know little about what such polls are used for and how reliable they are, especially in significant contexts like elections. Focusing on the 2020 presidential elections in the U.S., this study shows that outcomes of election polls on Twitter deviate from election results despite their prevalence. Leveraging demographic inference and statistical analysis, we find that Twitter polls are disproportionately authored by older males and exhibit a large bias towards candidate Donald Trump relative to representative mainstream polls. We investigate potential sources of biased outcomes from the point of view of inauthentic, automated, and counter-normative behavior. Using social media experiments and interviews with poll authors, we identify inconsistencies between public vote counts and those privately visible to poll authors, with the gap potentially attributable to purchased votes. We also find that Twitter accounts participating in election polls are more likely to be bots, and election poll outcomes tend to be more biased, before the election day than after. Finally, we identify instances of polls spreading voter fraud conspiracy theories and estimate that a couple thousand of such polls were posted in 2020. The study discusses the implications of biased election polls in the context of transparency and accountability of social media platforms., Comment: 14 pages, 10 figures

The primary goal of online change detection (OCD) is to promptly identify changes in the data stream. OCD problem find a wide variety of applications in diverse areas, e.g., security detection in smart grids and intrusion detection in communication networks. Prior research usually assumes precise knowledge of the system parameters. Nevertheless, this presumption often proves unattainable in practical scenarios due to factors such as estimation errors, system updates, etc. This paper aims to take the first attempt to develop a triadic-OCD framework with certifiable robustness, provable optimality, and guaranteed convergence. In addition, the proposed triadic-OCD algorithm can be realized in a fully asynchronous distributed manner, easing the necessity of transmitting the data to a single server. This asynchronous mechanism could also mitigate the straggler issue that faced by traditional synchronous algorithm. Moreover, the non-asymptotic convergence property of Triadic-OCD is theoretically analyzed, and its iteration complexity to achieve an $\epsilon$-optimal point is derived. Extensive experiments have been conducted to elucidate the effectiveness of the proposed method., Comment: Accepted at ICML2024

Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during training, resulting in significantly inferior performance compared with fully-supervised spotting. To bridge this gap, we propose a point-level weakly-supervised expression spotting (PWES) framework, where each expression requires to be annotated with only one random frame (i.e., a point). To mitigate the issue of sparse label distribution, the prevailing solution is pseudo-label mining, which, however, introduces new problems: localizing contextual background snippets results in inaccurate boundaries and discarding foreground snippets leads to fragmentary predictions. Therefore, we design the strategies of multi-refined pseudo label generation (MPLG) and distribution-guided feature contrastive learning (DFCL) to address these problems. Specifically, MPLG generates more reliable pseudo labels by merging class-specific probabilities, attention scores, fused features, and point-level labels. DFCL is utilized to enhance feature similarity for the same categories and feature variability for different categories while capturing global representations across the entire datasets. Extensive experiments on the CAS(ME)^2, CAS(ME)^3, and SAMM-LV datasets demonstrate PWES achieves promising performance comparable to that of recent fully-supervised methods.

Artificial quantum systems have emerged as indispensable platforms to realize exotic topological matter in a well-controlled manner. Here, we demonstrate topological quantum Heisenberg spin lattices, engineered with spin chains and two-dimensional spin arrays using spin 1/2 atoms on insulating films in a scanning tunnelling microscope (STM). We engineered with atomic precision both topological and trivial phases of the quantum spin model, realizing first- and second-order topological quantum magnets. Their many-body excitations were probed by single-atom electron spin resonance with ultrahigh energy resolution. The atomically-localized magnetic field of the STM tip allows us to directly visualize various topological bound modes including topological edge states, topological defects, and higher-order corner modes. Our results provide an important bottom-up approach to simulating exotic quantum many-body phases of interacting spins., Comment: Nature Nanotechnology (2024)

As transformer-based language models are trained on increasingly large datasets and with vast numbers of parameters, finding more efficient alternatives to the standard Transformer has become very valuable. While many efficient Transformers and Transformer alternatives have been proposed, none provide theoretical guarantees that they are a suitable replacement for the standard Transformer. This makes it challenging to identify when to use a specific model and what directions to prioritize for further investigation. In this paper, we aim to understand the capabilities and limitations of efficient Transformers, specifically the Sparse Transformer and the Linear Transformer. We focus on their reasoning capability as exhibited by Chain-of-Thought (CoT) prompts and follow previous works to model them as Dynamic Programming (DP) problems. Our results show that while these models are expressive enough to solve general DP tasks, contrary to expectations, they require a model size that scales with the problem size. Nonetheless, we identify a class of DP problems for which these models can be more efficient than the standard Transformer. We confirm our theoretical results through experiments on representative DP tasks, adding to the understanding of efficient Transformers' practical strengths and weaknesses.

With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density of natural language and limited model understanding ability. To alleviate this issue, we formulate the BATON, a framework designed to enhance the alignment between generated audio and text prompt using human preference feedback. Our BATON comprises three key stages: Firstly, we curated a dataset containing both prompts and the corresponding generated audio, which was then annotated based on human feedback. Secondly, we introduced a reward model using the constructed dataset, which can mimic human preference by assigning rewards to input text-audio pairs. Finally, we employed the reward model to fine-tune an off-the-shelf text-to-audio model. The experiment results demonstrate that our BATON can significantly improve the generation quality of the original text-to-audio models, concerning audio integrity, temporal relationship, and alignment with human preference.

In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position, our BiPE blends an intra-segment encoding and an inter-segment encoding. The intra-segment encoding identifies the locations within a segment and helps the model capture the semantic information therein via absolute positional encoding. The inter-segment encoding specifies the segment index, models the relationships between segments, and aims to improve extrapolation capabilities via relative positional encoding. Theoretical analysis shows this disentanglement of positional information makes learning more effective. The empirical results also show that our BiPE has superior length extrapolation capabilities across a wide range of tasks in diverse text modalities., Comment: 17 pages, 7 figures, 8 tables; ICML 2024 Camera Ready version; Code: https://github.com/zhenyuhe00/BiPE

Utilization of inter-base station cooperation for information processing has shown great potential in enhancing the overall quality of communication services (QoS) in wireless communication networks. Nevertheless, such cooperations require the knowledge of channel state information (CSI) at base stations (BSs), which is assumed to be perfectly known. However, CSI errors are inevitable in practice which necessitates beamforming techniques that can achieve robust performance in the presence of channel estimation errors. Existing approaches relax the robust beamforming design problems into semidefinite programming (SDP), which can only achieve a solution that is far from being optimal. To this end, this paper views robust beamforming design problems from a bilevel optimization perspective. In particular, we focus on maximizing the worst-case weighted sum-rate (WSR) in the downlink multi-cell multi-user multiple-input single-output (MISO) system considering bounded CSI errors. We first reformulate this problem into a bilevel optimization problem and then develop an efficient algorithm based on the cutting plane method. A distributed optimization algorithm has also been developed to facilitate the parallel processing in practical settings. Numerical results are provided to confirm the effectiveness of the proposed algorithm in terms of performance and complexity, particularly in the presence of CSI uncertainties., Comment: accepted at AAAI2024

Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the "bonus inconsistency" issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of random networks and implicitly incorporating pseudo counts to improve the precision of bonus allocation. This refinement encourages agents to engage in more extensive exploration. Our method effectively mitigates the inconsistency issue without introducing significant computational overhead. Both theoretical analysis and experimental results demonstrate the superiority of our approach over the original RND algorithm. Our method excels in challenging online exploration scenarios and effectively serves as an anti-exploration mechanism in D4RL offline tasks. Our code is publicly available at https://github.com/yk7333/DRND., Comment: ICML 2024 accepted

Recent advancements in generative artificial intelligence (AI) have raised concerns about their potential to create convincing fake social media accounts, but empirical evidence is lacking. In this paper, we present a systematic analysis of Twitter (X) accounts using human faces generated by Generative Adversarial Networks (GANs) for their profile pictures. We present a dataset of 1,420 such accounts and show that they are used to spread scams, spam, and amplify coordinated messages, among other inauthentic activities. Leveraging a feature of GAN-generated faces -- consistent eye placement -- and supplementing it with human annotation, we devise an effective method for identifying GAN-generated profiles in the wild. Applying this method to a random sample of active Twitter users, we estimate a lower bound for the prevalence of profiles using GAN-generated faces between 0.021% and 0.044% -- around 10K daily active accounts. These findings underscore the emerging threats posed by multimodal generative AI. We release the source code of our detection method and the data we collect to facilitate further investigation. Additionally, we provide practical heuristics to assist social media users in recognizing such accounts., Comment: 18 pages, 6 figures; added a new dataset and made some minor revisions

To investigate whether disk-mediated accretion is the primary mechanism in high-mass star formation, we have established a survey of a large sample of massive dense cores within a giant molecular cloud. We used high angular resolution ($\sim 1.8''$) observations with SMA to study the dust emission and molecular line emission of about 50 massive dense cores in Cygnus-X. At a typical distance of 1.4 kpc for Cygnus-X, these massive dense cores are resolved into $\sim 2000$ au condensations. We combined the CO outflow emission and gas kinematics traced by several high-density tracers to search for disk candidates. We extracted hundreds of dust condensations from the SMA 1.3 mm dust continuum emission. The CO data show bipolar or unipolar outflow signatures toward 49 dust condensations. Among them, only 27 sources are detected in dense gas tracers, which reveals the gas kinematics, and nine sources show evidence of rotating envelopes, suggesting the existence of embedded accretion disks. The position-velocity diagrams along the velocity gradient of all rotating condensations suggest that four condensations are possible to host Keplerian-like disks. A detailed investigation of the 27 sources detected in dense gas tracers suggests that the nine disk candidates are at earlier evolutionary stages compared to the remaining 18 sources. Non-detection of rotating disks in our sample may be due to several factors, including an unknown inclination angle of the rotation axis and an early evolutionary stage of the central source, and the latter could be important, considering that young and powerful outflows could confuse the observational evidence for rotation. The detection rate of disk candidates in our sample is 1/3, which confirms that disk accretion is a viable mechanism for high-mass star formation, although it may not be the only one., Comment: 19 pages, 12 figures, accepted for publication in A&A

While social media are a key source of data for computational social science, their ease of manipulation by malicious actors threatens the integrity of online information exchanges and their analysis. In this Chapter, we focus on malicious social bots, a prominent vehicle for such manipulation. We start by discussing recent studies about the presence and actions of social bots in various online discussions to show their real-world implications and the need for detection methods. Then we discuss the challenges of bot detection methods and use Botometer, a publicly available bot detection tool, as a case study to describe recent developments in this area. We close with a practical guide on how to handle social bots in social media research., Comment: This is a draft of the chapter. The final version will be available in the Handbook of Computational Social Science edited by Taha Yasseri, forthcoming 2024, Edward Elgar Publishing Ltd. The material cannot be used for any other purpose without further permission of the publisher and is for private use only

Deuterated molecules are valuable probes for investigating the evolution and the kinematics in the earliest stages of star formation. In this study, we conduct a comprehensive investigation by performing a single point survey of 101 starless clump candidates, and carrying out on-the-fly (OTF) observations of 11 selected sources, focusing on deuterated molecular lines using the IRAM 30-m telescope. In the single-point observation, we make 46 detections for DCO$^{+}$ J=1$-$0, 12 for DCN J=1$-$0, 51 for DNC J=1$-$0, 7 for N$_{2}$D$^{+}$ J=1$-$0, 20 for DCO$^{+}$ J=2$-$1, and 10 for DCN J=2$-$1. The starless clump candidates (SCCs) with deuterated molecule detections exhibit lower median kinetic temperatures and narrower H$_{2}$CO (1$_{(0,1)}$$-$0$_{(0,0)}$) median full width at half maximum (FWHM) compared to those without such detections, while simultaneously displaying similar median values of 1.1mm intensity, mass, and distance. Furthermore, our OTF observations reveal that deuterated molecules predominantly have peaks near the 1.1mm continuum peaks, with the DCO$^{+}$ J=1$-$0 emission demonstrating higher intensity in the deuterated peak region compared to the DCN and DNC J=1$-$0 emissions. Additionally, the majority of emissions from deuterated molecules and $^{13}$C$-$isotopologues exhibit peak positions close to those of the 1.1mm continuum peaks. By analyzing the 20"$\times$20" regions with strongest deuterated emissions in the OTF observations, we estimated deuterated abundances of 0.004$-$0.045, 0.011$-$0.040, and 0.004$-$0.038 for D$_{\rm frac}$(HCN), D$_{\rm frac}$(HCO$^{+}$), and D$_{\rm frac}$(HNC), respectively. The differential detection of deuterated molecular lines in our OTF observations could be attributed to variations in critical densities and formation pathways., Comment: 75 pages, 56 figures, 8 tables; accepted for publication in ApJS

We identify 182 flares on 158 stars within 100 pc of the Sun in both the near-ultraviolet (NUV: 1750-2750 \r{A}) and far-ultraviolet (FUV: 1350-1750 \r{A}) using high-cadence light curves from the Galaxy Evolution Explorer (GALEX). Ultraviolet (UV) emission from stellar flares plays a crucial role in determining the habitability of exoplanetary systems. However, whether such UV emission promotes or threatens such life depends strongly on the energetics of these flares. Most studies assessing the effect of flares on planetary habitability assume a 9000 K blackbody spectral energy distribution that produces more NUV flux than FUV flux ($R \equiv F_{\rm FUV} / F_{\rm NUV} \approx \frac{1}{6}$). Instead, we observe the opposite with the excess FUV reaching $R \approx \frac{1}{2} - 2$, roughly $3-12$ times the expectation of a 9000 K blackbody. The ratio of FUV to NUV time-integrated flare energies is 3.0 times higher on average than would be predicted by a constant 9000 K blackbody during the flare. Finally, we find that the FUV/NUV ratio at peak tentatively correlates ($\sim 2 \sigma$ significance) both with total UV flare energy and with the G - RP color of the host star. On average, we observe higher FUV/NUV ratios at peak in $E_{\text{UV}}>10^{32}$ erg flares and in flares on fully convective stars., Comment: Submitted to MNRAS, comments welcome

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $\mu$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $\mu$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $\mu$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $\epsilon$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{\epsilon^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$., Comment: Accepted at AAAI 2024

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

While researchers often study message features like moral content in text, such as party manifestos and social media, their quantification remains a challenge. Conventional human coding struggles with scalability and intercoder reliability. While dictionary-based methods are cost-effective and computationally efficient, they often lack contextual sensitivity and are limited by the vocabularies developed for the original applications. In this paper, we present an approach to construct vec-tionary measurement tools that boost validated dictionaries with word embeddings through nonlinear optimization. By harnessing semantic relationships encoded by embeddings, vec-tionaries improve the measurement of message features from text, especially those in short format, by expanding the applicability of original vocabularies to other contexts. Importantly, a vec-tionary can produce additional metrics to capture the valence and ambivalence of a message feature beyond its strength in texts. Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and word embedding methods and to produce measurements better aligned with crowdsourced human assessments. Furthermore, additional metrics from the vec-tionary unveiled unique insights that facilitated predicting outcomes such as message retransmission.

The SiO emissions are usually used to trace high-velocity outflow shocks in star-forming regions. However, several studies have found low-velocity and widespread SiO emissions not associated with outflows in molecular clouds. We aim to detect and characterize the SiO emissions in massive dense cores (MDCs), and explore the properties of the central sources of SiO emission. We present high-angular-resolution ($\sim$1.5$^{\prime\prime}$) observations of the SiO (5$-$4) line made with the Submillimeter Array towards a sample of 48 MDCs in the Cygnus-X star-forming complex. We studied the SiO emission structures, including their morphologies, kinematics, and energetics, and investigated their relationship with the evolution of the central sources. The SiO (5$-$4) emission is detected in 16 out of 48 MDCs. We identify 14 bipolar and 18 unipolar SiO (5$-$4) outflows associated with 29 dust condensations. Most outflows (24 out of 32) are associated with excess Spitzer 4.5 $\mu$m emissions. We also find diffuse low-velocity ($\Delta{v}$ $\le$ 1.2 km s$^{-1}$) SiO (5$-$4) emission closely surrounding the dust condensations in two MDCs, and suggest that it may originate from decelerated outflow shocks or large-scale shocks from global cloud collapse. We find that the SMA SiO (5$-$4) emission in MDCs is mostly associated with outflows. Probably due to the relatively high excitation of SiO (5$-$4) compared to SiO (2$-$1) and due to the spatial filtering effect, we do not detect large-scale low-velocity SiO (5$-$4) emission, but detect more compact low-velocity emission in close proximity to the dust condensations. We group the sources into different evolutionary stages based on the infrared emission, radio continuum emission, and gas temperature properties of the outflow central sources, and find that the 24 $\mu$m luminosity tends to increase with evolution., Comment: 47 pages, 24 figures,4 tables, accepted for publication in A&A

Uplift modeling refers to the set of machine learning techniques that a manager may use to estimate customer uplift, that is, the net effect of an action on some customer outcome. By identifying the subset of customers for whom a treatment will have the greatest effect, uplift models assist decision-makers in optimizing resource allocations and maximizing overall returns. Accurately estimating customer uplift poses practical challenges, as it requires assessing the difference between two mutually exclusive outcomes for each individual. In this paper, we propose two innovative adaptations of the well-established Gradient Boosting Decision Trees (GBDT) algorithm, which learn the causal effect in a sequential way and overcome the counter-factual nature. Both approaches innovate existing techniques in terms of ensemble learning method and learning objectives, respectively. Experiments on large-scale datasets demonstrate the usefulness of the proposed methods, which often yielding remarkable improvements over base models. To facilitate the application, we develop the UTBoost, an end-to-end tree boosting system specifically designed for uplift modeling. The package is open source and has been optimized for training speed to meet the needs of real industrial applications., Comment: 11 pages, 3 figures

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to fine-tune the underlying models. However, crafting an efficient reward model demands extensive datasets, optimal architecture, and manual hyperparameter tuning, making the process both time and cost-intensive. The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model. However, the extensive GPU memory requirement of the diffusion model's denoising process hinders the direct application of the DPO method. To address this issue, we introduce the Direct Preference for Denoising Diffusion Policy Optimization (D3PO) method to directly fine-tune diffusion models. The theoretical analysis demonstrates that although D3PO omits training a reward model, it effectively functions as the optimal reward model trained using human feedback data to guide the learning process. This approach requires no training of a reward model, proving to be more direct, cost-effective, and minimizing computational overhead. In experiments, our method uses the relative scale of objectives as a proxy for human preference, delivering comparable results to methods using ground-truth rewards. Moreover, D3PO demonstrates the ability to reduce image distortion rates and generate safer images, overcoming challenges lacking robust reward models. Our code is publicly available at https://github.com/yk7333/D3PO., Comment: CVPR 2024 accepted; huggingface daily paper

To understand the relation between NH$_2$D and its physical environment, we mapped ortho-NH$_2$D $1_{11}^s-1_{01}^a$ at 85.9 GHz toward 24 Galactic late-stage massive star-forming regions with Institut de Radioastronomie Millim$ \'e$trique (IRAM) 30-m telescope. Ortho-NH$_2$D $1_{11}^s-1_{01}^a$ was detected in 18 of 24 sources. Comparing with the distribution of H$^{13}$CN 1-0 as a dense gas tracer and radio recombination line H42$\alpha$, ortho-NH$_2$D $1_{11}^s-1_{01}^a$ present complex and diverse spatial distribution in these targets. 11 of the 18 targets, present a different distribution between ortho-NH$_2$D $1_{11}^s-1_{01}^a$ and H$^{13}$CN 1-0, while no significant difference between these two lines can be found in the other 7 sources, mainly due to limited spatial resolution and sensitivity. Moreover, with H42$\alpha$ tracing massive young stellar objects, ortho-NH$_2$D $1_{11}^s-1_{01}^a$ seems to show a relatively weak emission near the massive young stellar objects., Comment: 30 pages, 20 figures, 4 tables. Accepted to MNRAS

Subject to intricate environmental variables, the precise classification of jamming signals holds paramount significance in the effective implementation of anti-jamming strategies within communication systems. In light of this imperative, we propose an innovative fusion algorithm based on conditional generative adversarial network (CGAN) and convolutional neural network (CNN), which aims to deal with the difficulty in applying deep learning (DL) algorithms due to the instantaneous nature of jamming signals in practical communication systems. Compared with previous methods, our algorithm embeds jamming category labels to constrain the range of generated signals in the frequency domain by using the CGAN model, which simultaneously captures potential label information while learning the distribution of signal data thus achieves an 8% improvement in accuracy even when working with a few-sample dataset. Real-world satellite communication scenarios are simulated by adopting hardware platform, and we validate our algorithm by using the resulting time-domain waveform data. The experimental results indicate that our algorithm still performs extremely well, which demonstrates significant potential for practical application in real-world communication scenarios., Comment: Required to supplement the experiments in Section VII, enhance the notations in Table I, and make necessary adjustments to Equation 17 to ensure accuracy and completeness

Crocodiles, known as one of the oldest and most resilient species on Earth, have demonstrated remarkable locomotor abilities both on land and in water, evolving over millennia to adapt to diverse environments. In this paper, we draw inspiration from crocodiles and introduce a highly biomimetic crocodile robot equipped with multiple degrees of freedom and articulated trunk joints. This design is based on a comprehensive analysis of the structural and motion characteristics observed in real crocodiles. The bionic crocodile robot has the problem of limb-torso incoordination during movement, in order to solve this problem, we apply the D-H method for both forward and inverse kinematics analysis of the robot's legs and spine. Through a series of simulation experiments, we investigate the robot's stability of motion, fault tolerance, and adaptability to the environment in two motor pattern: with and without the involvement of the spine and tail in its movements. Experiment results demonstrate that the bionic crocodile robot exhibits superior motion performance when the spine and tail cooperate with the extremities. This research not only showcases the potential of biomimicry in robotics but also underscores the significance of understanding how nature's designs can inform and enhance our technological innovations.

M-dwarf flares observed by the \textit{Transiting Exoplanet Survey Satellite} (\textit{TESS}) sometimes exhibit a "peak-bump" light-curve morphology, characterized by a secondary, gradual peak well after the main, impulsive peak. A similar "late phase" is frequently detected in solar flares observed in the extreme-ultraviolet from longer hot coronal loops distinct from the impulsive flare structures. White-light emission has also been observed in off-limb solar flare loops. Here, we perform a suite of one-dimensional hydrodynamic loop simulations for M-dwarf flares inspired by these solar examples. Our results suggest that coronal plasma condensation following impulsive flare heating can yield high electron number density in the loop, allowing it to contribute significantly to the optical light curves via free-bound and free-free emission mechanisms. Our simulation results qualitatively agree with \textit{TESS} observations: the longer evolutionary time scale of coronal loops produces a distinct, secondary emission peak; its intensity increases with the injected flare energy. We argue that coronal plasma condensation is a possible mechanism for the \textit{TESS} late-phase flares., Comment: 31 pages, 13 figures, accepted for publication in ApJ

Stable imaging in adverse environments (e.g., total darkness) makes thermal infrared (TIR) cameras a prevalent option for night scene perception. However, the low contrast and lack of chromaticity of TIR images are detrimental to human interpretation and subsequent deployment of RGB-based vision algorithms. Therefore, it makes sense to colorize the nighttime TIR images by translating them into the corresponding daytime color images (NTIR2DC). Despite the impressive progress made in the NTIR2DC task, how to improve the translation performance of small object classes is under-explored. To address this problem, we propose a generative adversarial network incorporating feedback-based object appearance learning (FoalGAN). Specifically, an occlusion-aware mixup module and corresponding appearance consistency loss are proposed to reduce the context dependence of object translation. As a representative example of small objects in nighttime street scenes, we illustrate how to enhance the realism of traffic light by designing a traffic light appearance loss. To further improve the appearance learning of small objects, we devise a dual feedback learning strategy to selectively adjust the learning frequency of different samples. In addition, we provide pixel-level annotation for a subset of the Brno dataset, which can facilitate the research of NTIR image understanding under multiple weather conditions. Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task., Comment: 14 pages, 14 figures. arXiv admin note: text overlap with arXiv:2208.02960

The use of machine learning (ML) models to assess and score textual data has become increasingly pervasive in an array of contexts including natural language processing, information retrieval, search and recommendation, and credibility assessment of online content. A significant disruption at the intersection of ML and text are text-generating large-language models such as generative pre-trained transformers (GPTs). We empirically assess the differences in how ML-based scoring models trained on human content assess the quality of content generated by humans versus GPTs. To do so, we propose an analysis framework that encompasses essay scoring ML-models, human and ML-generated essays, and a statistical model that parsimoniously considers the impact of type of respondent, prompt genre, and the ML model used for assessment model. A rich testbed is utilized that encompasses 18,460 human-generated and GPT-based essays. Results of our benchmark analysis reveal that transformer pretrained language models (PLMs) more accurately score human essay quality as compared to CNN/RNN and feature-based ML methods. Interestingly, we find that the transformer PLMs tend to score GPT-generated text 10-15\% higher on average, relative to human-authored documents. Conversely, traditional deep learning and feature-based ML models score human text considerably higher. Further analysis reveals that although the transformer PLMs are exclusively fine-tuned on human text, they more prominently attend to certain tokens appearing only in GPT-generated text, possibly due to familiarity/overlap in pre-training. Our framework and results have implications for text classification settings where automated scoring of text is likely to be disrupted by generative AI., Comment: Data available at: https://github.com/nd-hal/automated-ML-scoring-versus-generation

This paper proposes a fast dual-layer lossless coding for high dynamic range images (HDRIs) in the Radiance format. The coding, which consists of a base layer and a lossless enhancement layer, provides a standard dynamic range image (SDRI) without requiring an additional algorithm at the decoder and can losslessly decode the HDRI by adding the residual signals (residuals) between the HDRI and SDRI to the SDRI, if desired. To suppress the dynamic range of the residuals in the enhancement layer, the coding directly uses the mantissa and exponent information from the Radiance format. To further reduce the residual energy, each mantissa is modeled (estimated) as a linear function, i.e., a simple linear regression, of the encoded-decoded SDRI in each region with the same exponent. This is called simple linear regressive mantissa estimator. Experimental results show that, compared with existing methods, our coding reduces the average bitrate by approximately $1.57$-$6.68$ % and significantly reduces the average encoder implementation time by approximately $87.13$-$98.96$ %.

Solar eruptive activities could occur in weak magnetic field environments and over large spatial scales, especially relevant to eruptions involving intermediate or quiescent solar filaments. To handle the large scales, we implement and apply a flux rope embedding method using regularized Biot-Savart laws in the spherical coordinate system. Combined with a potential field source surface model and a magneto-frictional method, a nonlinear force-free field comprising a flux rope embedded in a potential field is constructed. Using the combined nonlinear force-free field as the initial condition, we then perform a zero-$\beta$ data-constrained magnetohydrodynamic (MHD) simulation for an M8.7 flare at 03:38 UT on 2012 January 23. The MHD model reproduces the eruption process, flare ribbon evolution (represented by the quasi-separatrix layer evolution) and kinematics of the flux rope. This approach could potentially model global-scale eruptions from weak field regions., Comment: 23 pages, 7 figures, accepted for publicaiton in ApJ

Fact checking can be an effective strategy against misinformation, but its implementation at scale is impeded by the overwhelming volume of information online. Recent artificial intelligence (AI) language models have shown impressive ability in fact-checking tasks, but how humans interact with fact-checking information provided by these models is unclear. Here, we investigate the impact of fact-checking information generated by a popular large language model (LLM) on belief in, and sharing intent of, political news headlines in a preregistered randomized control experiment. Although the LLM accurately identifies most false headlines (90%), we find that this information does not significantly improve participants' ability to discern headline accuracy or share accurate news. In contrast, viewing human-generated fact checks enhances discernment in both cases. Subsequent analysis reveals that the AI fact-checker is harmful in specific cases: it decreases beliefs in true headlines that it mislabels as false and increases beliefs in false headlines that it is unsure about. On the positive side, AI fact-checking information increases the sharing intent for correctly labeled true headlines. When participants are given the option to view LLM fact checks and choose to do so, they are significantly more likely to share both true and false news but only more likely to believe false headlines. Our findings highlight an important source of potential harm stemming from AI applications and underscore the critical need for policies to prevent or mitigate such unintended consequences.

Foundation models (FMs) have exhibited remarkable performance across a wide range of downstream tasks in many domains. Nevertheless, general-purpose FMs often face challenges when confronted with domain-specific problems, due to their limited access to the proprietary training data in a particular domain. In biomedicine, there are various biological modalities, such as molecules, proteins, and cells, which are encoded by the language of life and exhibit significant modality gaps with human natural language. In this paper, we introduce BioMedGPT, an open multimodal generative pre-trained transformer (GPT) for biomedicine, to bridge the gap between the language of life and human natural language. BioMedGPT allows users to easily ``communicate'' with diverse biological modalities through free text, which is the first of its kind. BioMedGPT aligns different biological modalities with natural language via a large generative language model, namely, BioMedGPT-LM. We publish BioMedGPT-10B, which unifies the feature spaces of molecules, proteins, and natural language via encoding and alignment. Through fine-tuning, BioMedGPT-10B outperforms or is on par with human and significantly larger general-purpose foundation models on the biomedical QA task. It also demonstrates promising performance in the molecule QA and protein QA tasks, which could greatly accelerate the discovery of new drugs and therapeutic targets. In addition, BioMedGPT-LM-7B is the first large generative language model based on Llama2 in the biomedical domain, therefore is commercial friendly. Both BioMedGPT-10B and BioMedGPT-LM-7B are open-sourced to the research community. In addition, we publish the datasets that are meticulously curated for the alignment of multi-modalities, i.e., PubChemQA and UniProtQA. All the models, codes, and datasets are available at \url{https://github.com/PharMolix/OpenBioMed}., Comment: 12 pages, 4 figures

Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information. However, Graph Contrastive Learning (GCL) methods, which tackle the label problem effectively, mainly focus on the feature information of the global graph or small subgraph structure (e.g., the first-order neighborhood). In the paper, we propose a Local Structure-aware Graph Contrastive representation Learning method (LS-GCL) to model the structural information of nodes from multiple views. Specifically, we construct the semantic subgraphs that are not limited to the first-order neighbors. For the local view, the semantic subgraph of each target node is input into a shared GNN encoder to obtain the target node embeddings at the subgraph-level. Then, we use a pooling function to generate the subgraph-level graph embeddings. For the global view, considering the original graph preserves indispensable semantic information of nodes, we leverage the shared GNN encoder to learn the target node embeddings at the global graph-level. The proposed LS-GCL model is optimized to maximize the common information among similar instances at three various perspectives through a multi-level contrastive loss function. Experimental results on five datasets illustrate that our method outperforms state-of-the-art graph representation learning approaches for both node classification and link prediction tasks.

Large language models (LLMs) exhibit impressive capabilities in generating realistic text across diverse subjects. Concerns have been raised that they could be utilized to produce fake content with a deceptive intention, although evidence thus far remains anecdotal. This paper presents a case study about a Twitter botnet that appears to employ ChatGPT to generate human-like content. Through heuristics, we identify 1,140 accounts and validate them via manual annotation. These accounts form a dense cluster of fake personas that exhibit similar behaviors, including posting machine-generated content and stolen images, and engage with each other through replies and retweets. ChatGPT-generated content promotes suspicious websites and spreads harmful comments. While the accounts in the AI botnet can be detected through their coordination patterns, current state-of-the-art LLM content classifiers fail to discriminate between them and human accounts in the wild. These findings highlight the threats posed by AI-enabled social bots.

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the federated distributionally robust optimization (FDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance., Comment: arXiv admin note: substantial text overlap with arXiv:2210.07588

Molecular knowledge resides within three different modalities of information sources: molecular structures, biomedical documents, and knowledge bases. Effective incorporation of molecular knowledge from these modalities holds paramount significance in facilitating biomedical research. However, existing multimodal molecular foundation models exhibit limitations in capturing intricate connections between molecular structures and texts, and more importantly, none of them attempt to leverage a wealth of molecular expertise derived from knowledge graphs. In this study, we introduce MolFM, a multimodal molecular foundation model designed to facilitate joint representation learning from molecular structures, biomedical texts, and knowledge graphs. We propose cross-modal attention between atoms of molecular structures, neighbors of molecule entities and semantically related texts to facilitate cross-modal comprehension. We provide theoretical analysis that our cross-modal pre-training captures local and global molecular knowledge by minimizing the distance in the feature space between different modalities of the same molecule, as well as molecules sharing similar structures or functions. MolFM achieves state-of-the-art performance on various downstream tasks. On cross-modal retrieval, MolFM outperforms existing models with 12.13% and 5.04% absolute gains under the zero-shot and fine-tuning settings, respectively. Furthermore, qualitative analysis showcases MolFM's implicit ability to provide grounding from molecular substructures and knowledge graphs. Code and models are available on https://github.com/BioFM/OpenBioMed., Comment: 31 pages, 15 figures, and 15 tables

Most micro- and macro-expression spotting methods in untrimmed videos suffer from the burden of video-wise collection and frame-wise annotation. Weakly-supervised expression spotting (WES) based on video-level labels can potentially mitigate the complexity of frame-level annotation while achieving fine-grained frame-level spotting. However, we argue that existing weakly-supervised methods are based on multiple instance learning (MIL) involving inter-modality, inter-sample, and inter-task gaps. The inter-sample gap is primarily from the sample distribution and duration. Therefore, we propose a novel and simple WES framework, MC-WES, using multi-consistency collaborative mechanisms that include modal-level saliency, video-level distribution, label-level duration and segment-level feature consistency strategies to implement fine frame-level spotting with only video-level labels to alleviate the above gaps and merge prior knowledge. The modal-level saliency consistency strategy focuses on capturing key correlations between raw images and optical flow. The video-level distribution consistency strategy utilizes the difference of sparsity in temporal distribution. The label-level duration consistency strategy exploits the difference in the duration of facial muscles. The segment-level feature consistency strategy emphasizes that features under the same labels maintain similarity. Experimental results on three challenging datasets -- CAS(ME)$^2$, CAS(ME)$^3$, and SAMM-LV -- demonstrate that MC-WES is comparable to state-of-the-art fully-supervised methods.

Previously, the existence of ground state solutions of a family of systems of Klein-Gordon equations has been widely studied. In this article, we will study the linearized operator at the ground state and give a complete description of the spectrum for this operator in the radial case: the existence of a unique negative eigenvalue, no resonance at '1'(the bottom of the essential spectrum), no embedded eigenvalue in the essential spectrum and the spectral gap property (i.e., there is no eigenvalue in the interval (0,1]).

The research fields of parametric face model and 3D face reconstruction have been extensively studied. However, a critical question remains unanswered: how to tailor the face model for specific reconstruction settings. We argue that reconstruction with multi-view uncalibrated images demands a new model with stronger capacity. Our study shifts attention from data-dependent 3D Morphable Models (3DMM) to an understudied human-designed skinning model. We propose Adaptive Skinning Model (ASM), which redefines the skinning model with more compact and fully tunable parameters. With extensive experiments, we demonstrate that ASM achieves significantly improved capacity than 3DMM, with the additional advantage of model size and easy implementation for new topology. We achieve state-of-the-art performance with ASM for multi-view reconstruction on the Florence MICC Coop benchmark. Our quantitative analysis demonstrates the importance of a high-capacity model for fully exploiting abundant information from multi-view input in reconstruction. Furthermore, our model with physical-semantic parameters can be directly utilized for real-world applications, such as in-game avatar creation. As a result, our work opens up new research direction for parametric face model and facilitates future research on multi-view reconstruction., Comment: 18 pages

In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery. However, these methods partly lag behind real-world pharmaceutical approaches of human experts that additionally grasp structured knowledge from knowledge bases and unstructured knowledge from biomedical literature. To bridge this gap, we propose KEDD, a unified, end-to-end, and multimodal deep learning framework that optimally incorporates both structured and unstructured knowledge for vast AI drug discovery tasks. The framework first extracts underlying characteristics from heterogeneous inputs, and then applies multimodal fusion for accurate prediction. To mitigate the problem of missing modalities, we leverage multi-head sparse attention and a modality masking mechanism to extract relevant information robustly. Benefiting from integrated knowledge, our framework achieves a deeper understanding of molecule entities, brings significant improvements over state-of-the-art methods on a wide range of tasks and benchmarks, and reveals its promising potential in assisting real-world drug discovery., Comment: 10 pages, 6 figures

Search engines increasingly leverage large language models (LLMs) to generate direct answers, and AI chatbots now access the Internet for fresh data. As information curators for billions of users, LLMs must assess the accuracy and reliability of different sources. This paper audits eight widely used LLMs from three major providers -- OpenAI, Google, and Meta -- to evaluate their ability to discern credible and high-quality information sources from low-credibility ones. We find that while LLMs can rate most tested news outlets, larger models more frequently refuse to provide ratings due to insufficient information, whereas smaller models are more prone to hallucination in their ratings. For sources where ratings are provided, LLMs exhibit a high level of agreement among themselves (average Spearman's $\rho = 0.81$), but their ratings align only moderately with human expert evaluations (average $\rho = 0.59$). Analyzing news sources with different political leanings in the US, we observe a liberal bias in credibility ratings yielded by all LLMs in default configurations. Additionally, assigning partisan identities to LLMs consistently results in strong politically congruent bias in the ratings. These findings have important implications for the use of LLMs in curating news and political information., Comment: 11 pages, 8 figures